The Agent Skills Directory

[SAFE]: The skill follows security best practices by explicitly prohibiting hardcoded secrets in test code and recommending the use of separate environment variables via .env.test files.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data as it takes user-specified frameworks, tools, and test targets to generate code.
Ingestion points: User input defined in the "Input Format" section of SKILL.md, including framework and test target descriptions.
Boundary markers: Absent; the instructions do not specify delimiters or validation for user-provided strings during code generation.
Capability inventory: The skill's intended use involves file system writes (test files) and package installation via standard package managers.
Sanitization: No explicit sanitization or escaping of user input is mentioned in the instructions.
[EXTERNAL_DOWNLOADS]: The skill references standard development dependencies including jest, supertest, and pytest. These are well-known testing frameworks installed via official registries, which is expected behavior for a testing-focused skill.

backend-testing